Search Awards

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds meaningful context beyond those annotations by characterizing the data as a sparse subset (~52K notices), self-reported, and potentially unrepresentative of a company's full award book. This directly informs interpretation of results and complements the openWorldHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and the critical caveat before moving to parameters. The bullet list is scannable and each sentence adds either selection guidance, data-quality context, or parameter semantics. No redundant restatement of the schema or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with no required parameters, the description covers the key selection context, data caveats, and most parameter semantics. An output schema exists, so return-value details are not needed. The only notable gap is pagination/offset behavior, which would be useful for agents working with large result sets.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description compensates well by listing most parameters with their meaning and format: awardee partial match, UEI, 6-digit NAICS, agency substring, USD for value bounds, and YYYY-MM-DD for dates. However, the 'offset' parameter is not mentioned, and pagination semantics beyond 'limit max 1000' are left undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource ('SAM Award Notices'), the question it answers ('who won, how much, when'), and its scope. It also explicitly contrasts itself with search_contracts, so an agent can immediately distinguish this tool from the most likely sibling alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance: use search_contracts for the comprehensive award record, and use search_awards specifically when the question concerns SAM-noticed awards. It also warns about the sparse, self-reported nature of the data, preventing misuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.